Merge tag 'nfs-for-4.3-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights include:

  Bugfixes:
   - Fix a use-after-free bug in the RPC/RDMA client
   - Fix a write performance regression
   - Fix up page writeback accounting
   - Don't try to reclaim unused state owners
   - Fix a NFSv4 nograce recovery hang
   - reset states to use open_stateid when returning delegation
     voluntarily
   - Fix a tracepoint NULL-pointer dereference"

* tag 'nfs-for-4.3-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Fix a tracepoint NULL-pointer dereference
  nfs4: reset states to use open_stateid when returning delegation voluntarily
  NFSv4: Fix a nograce recovery hang
  NFSv4.1: nfs4_opendata_check_deleg needs to handle NFS4_OPEN_CLAIM_DELEG_CUR_FH
  NFSv4: Don't try to reclaim unused state owners
  NFS: Fix a write performance regression
  NFS: Fix up page writeback accounting
  xprtrdma: disconnect and flush cqs before freeing buffers

6 files changed, 30 insertions, 15 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f93b9cd..5133bb1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1458,12 +1458,18 @@ nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state)
 	if (delegation)
 		delegation_flags = delegation->flags;
 	rcu_read_unlock();
-	if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
+	switch (data->o_arg.claim) {
+	default:
+		break;
+	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+	case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 		pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
 				   "returning a delegation for "
 				   "OPEN(CLAIM_DELEGATE_CUR)\n",
 				   clp->cl_hostname);
-	} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
+		return;
+	}
+	if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
 		nfs_inode_set_delegation(state->inode,
 					 data->owner->so_cred,
 					 &data->o_res);
@@ -1771,6 +1777,9 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
 	if (IS_ERR(opendata))
 		return PTR_ERR(opendata);
 	nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
+	write_seqlock(&state->seqlock);
+	nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+	write_sequnlock(&state->seqlock);
 	clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	switch (type & (FMODE_READ|FMODE_WRITE)) {
 	case FMODE_READ|FMODE_WRITE:
@@ -1863,6 +1872,8 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
 	data->rpc_done = 0;
 	data->rpc_status = 0;
 	data->timestamp = jiffies;
+	if (data->is_recover)
+		nfs4_set_sequence_privileged(&data->c_arg.seq_args);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5db3246..d854693 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1725,7 +1725,8 @@ restart:
 			if (!test_and_clear_bit(ops->owner_flag_bit,
 							&sp->so_flags))
 				continue;
-			atomic_inc(&sp->so_count);
+			if (!atomic_inc_not_zero(&sp->so_count))
+				continue;
 			spin_unlock(&clp->cl_lock);
 			rcu_read_unlock();
 
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 28df12e..671cf68 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -409,7 +409,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
 			__entry->flags = flags;
 			__entry->fmode = (__force unsigned int)ctx->mode;
 			__entry->dev = ctx->dentry->d_sb->s_dev;
-			if (!IS_ERR(state))
+			if (!IS_ERR_OR_NULL(state))
 				inode = state->inode;
 			if (inode != NULL) {
 				__entry->fileid = NFS_FILEID(inode);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 72624dc..75ab762 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -569,19 +569,17 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 	if (!nfs_pageio_add_request(pgio, req)) {
 		nfs_redirty_request(req);
 		ret = pgio->pg_error;
-	}
+	} else
+		nfs_add_stats(page_file_mapping(page)->host,
+				NFSIOS_WRITEPAGES, 1);
 out:
 	return ret;
 }
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
 {
-	struct inode *inode = page_file_mapping(page)->host;
 	int ret;
 
-	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
-	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
-
 	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
 	if (ret == -EAGAIN) {
@@ -597,9 +595,11 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st
 static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
 {
 	struct nfs_pageio_descriptor pgio;
+	struct inode *inode = page_file_mapping(page)->host;
 	int err;
 
-	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
+	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
+	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
 				false, &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
@@ -1223,7 +1223,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 		return 1;
 	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
 		       list_empty_careful(&flctx->flc_posix)))
-		return 0;
+		return 1;
 
 	/* Check to see if there are whole file write locks */
 	ret = 0;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 64443eb..41e452b 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -270,8 +270,8 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 
 	xprt_clear_connected(xprt);
 
-	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
 	rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
+	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
 	rpcrdma_ia_close(&r_xprt->rx_ia);
 
 	xprt_rdma_free_addresses(xprt);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index eb081ad..8a477e2 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -755,19 +755,22 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 
 	cancel_delayed_work_sync(&ep->rep_connect_worker);
 
-	if (ia->ri_id->qp) {
+	if (ia->ri_id->qp)
 		rpcrdma_ep_disconnect(ep, ia);
+
+	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+	rpcrdma_clean_cq(ep->rep_attr.send_cq);
+
+	if (ia->ri_id->qp) {
 		rdma_destroy_qp(ia->ri_id);
 		ia->ri_id->qp = NULL;
 	}
 
-	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
 	rc = ib_destroy_cq(ep->rep_attr.recv_cq);
 	if (rc)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, rc);
 
-	rpcrdma_clean_cq(ep->rep_attr.send_cq);
 	rc = ib_destroy_cq(ep->rep_attr.send_cq);
 	if (rc)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",